Structured learning of assignment models for neuron reconstruction to minimize topological errors
Tipus de documentText en actes de congrés
Condicions d'accésAccés obert
Structured learning provides a powerful framework for empirical risk minimization on the predictions of structured models. It allows end-to-end learning of model parameters to minimize an application specific loss function. This framework is particularly well suited for discrete optimization models that are used for neuron reconstruction from anisotropic electron microscopy (EM) volumes. However, current methods are still learning unary potentials by training a classifier that is agnostic about the model it is used in. We believe the reason for that lies in the difficulties of (1) finding a representative training sample, and (2) designing an application specific loss function that captures the quality of a proposed solution. In this paper, we show how to find a representative training sample from human generated ground truth, and propose a loss function that is suitable to minimize topological errors in the reconstruction. We compare different training methods on two challenging EM-datasets. Our structured learning approach shows consistently higher reconstruction accuracy than other current learning methods.
© 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
CitacióFunke, J., Klein, J., Moreno-Noguer, F., Cardona, A., Cook, M. Structured learning of assignment models for neuron reconstruction to minimize topological errors. A: IEEE International Symposium on Biomedical Imaging. "2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Proceedings". Praga: 2016, p. 607-611.
Versió de l'editorhttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7493341